#pdf

Typed structured extraction from PDFs, photos & text via any LLM — Instructor for Swift, document-first

Measurable image + document toolkit. Bit-exact SVG from flat art (SSIM 1.0000, verified by rendering it back); beats potrace, imagetracerjs and vtracer on photographs. 11 raster formats, every pair convertible. Cut-ready DXF with real physical size, EPS, PDF, G-code. PDF & Office rendering. MCP server for agents. Zero-dependency portable core.

Overleaf, but local: the compiled PDF, your coding agent, your disk, and any git remote.

Trust layer for document→JSON extraction & AI agents: calibrated per-field confidence + source grounding + accept/review abstention on any OCR/VLM. Ships VerifyDocBench, a novel grounding-conditioned conformal method, and an MCP server.

专供 AI 智能体访问本地研究文献库的 MCP。支持 PDF、Markdown、BibTeX、RIS、EndNote 及 XML 格式；具备自动索引、智能搜索及只读访问功能。MCP server for AI agents to access local research libraries. Supports PDF, Markdown, BibTeX, RIS, EndNote, XML. Auto-index, smart search, read-only.

A library desk for your files — and your agents. Local file toolkit + Claude Code plugin marketplace.

🔬 Private AI research assistant like Google NotebookLM but 100% local. Upload PDFs, URLs & YouTube. Ask questions grounded in your sources. 12-provider AI fallback. Works offline.

Official repository and downloads for PdfAgent — a native macOS app for downloading images and converting them to PDF or CBZ.

TeamSync PDF Viewer

AI-powered Resume Parser and Candidate Ranking System using Groq LLM, Pydantic, and Python to extract structured resume data, compare it against job descriptions, calculate match scores, and rank candidates automatically.

AI-powered Resume Analyzer using Streamlit, NLP, ATS scoring, Gemini AI, and PDF report generation.

A PDF Question Answering chatbot built with LangChain, FAISS, Hugging Face, and Streamlit using RAG

RAG em Python puro: PDF ingestion, OpenAI embeddings, SQLite vectorstore, cosine similarity, Claude generator. Sem LangChain.

A clinical mental health companion powered by FastAPI, Next.js 14, and native Android. Implements RAG via LangChain, Groq (Llama 3), and Cohere embeddings with real-time sentiment tracking, mood analytics, and PDF consultation reports.

MCP server for PDFMakerAPI — turn a description into a shareable, editable PDF (invoices, certificates, reports, resumes) from Claude, Cursor, and other MCP clients.

A Claude Code skill that builds typeset, single-column, parse-verified resumes from YAML. Re-extracts the finished PDF to prove the text layer survives — instead of just claiming 'ATS-friendly'.

Render Markdown to PDF matching the yzane Markdown-PDF VS Code extension — with Mermaid diagrams and embedded charts. CLI + AI-agent skill.

Stateful chunked QA-controlled document translation pipeline for Hermes Agent.

SynchroPage工作区：将 PDF 转为页级对齐的 lecture_pairpack JSON，提供 local-first React Reader、讲解编辑和 OpenAI Agent 面板。

Document parsing that never loses provenance: Markdown + JSON output where every block knows its source page, section, and location.

Hardcopy — browser extension to export your Claude chats (Chat, Cowork & Code sessions) as Markdown, PDF, Word, RTF and plain text. Fully client-side, zero telemetry. Not affiliated with Anthropic.